打造既受欢迎又不极化的新闻内容: 大语言模型驱动的多目标优化
发布时间：2026-01-22
1月
26
|
时间和日期
|
2026-01-26 (星期一) 10:30 上午
-
12:00 下午
|
|
地点
|
综合教学楼D504会议室
|
| 标题 | 打造既受欢迎又不极化的新闻内容: 大语言模型驱动的多目标优化 |
| 日期和时间 |
2026年1月26日（周一） 10:30-12:00 |
| 地点 | 综合教学楼D504会议室 |
| 主讲人 |
程梦婕 哈佛商学院 |
| 摘要 | We study how media firms can use LLMs to generate news content that aligns with multiple objectives – making content more engaging while maintaining a preferred level of polarization/slant consistent with the firm’s editorial policy. Using news articles from The New York Times, we first show that more engaging human-written content tends to be more polarizing. Further, naively employing LLMs (with prompts or standard Direct Preference Optimization approaches) to generate more engaging content can also increase polarization. This has an important managerial and policy implication: using LLMs without building in controls for limiting slant can exacerbate news media polarization. We present a constructive solution to this problem based on the Multi-Objective Direct Preference Optimization (MODPO) algorithm, a novel approach that integrates Direct Preference Optimization with multi-objective optimization techniques. We build on open-source LLMs and develop a new language model that simultaneously makes content more engaging while maintaining a preferred editorial stance. Our model achieves this by modifying content characteristics strongly associated with polarization but that have a relatively smaller impact on engagement. Our approach and findings apply to other settings where firms seek to use LLMs for content creation to achieve multiple objectives, e.g., advertising and social media. |
| 主讲人简介 | 程梦婕目前是哈佛商学院的博士生。她的研究聚焦于内容营销、数字营销以及人工智能。她致力于将经济学原理与消费者行为学融入大型语言模型、机器学习和因果推断的技术框架中，为数字时代的营销战略提供科学且可执行的解决方案。在开始学术旅程之前，她曾任职于 Facebook，在广告与知识图谱团队担任机器学习工程师，推动平台广告系统与智能助手的研发。她本科毕业于浙江大学竺可桢学院金融学专业，并于斯坦福大学获得管理科学与工程硕士学位。 |
